© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-TRANSCODER-262K
    4. 49137
    Prev
    Next
    INDEX
    Explanations

    file paths following keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     サングラス
    0.37
    另一方面
    0.36
     *:
    0.33
    િસ્
    0.33
    િજા
    0.32
    నర్
    0.31
    EventListeners
    0.30
    㳒
    0.30
    Dijstra
    0.30
     크라운
    0.30
    POSITIVE LOGITS
    /
    1.50
    /
    0.84
    หรือ
    0.82
    或
    0.80
     или
    0.78
     /
    0.78
    /-
    0.77
    /(
    0.77
     किंवा
    0.73
    /{
    0.72
    Activations Density 0.007%

    No Known Activations